Martin Van Waerebeke

collaborators

2 papers

cs.LG2026

Variance-Reduced $(ε, I^´) -$ Unlearning using Forget Set Gradients

Martin Van Waerebeke, Marco Lorenzi, Kevin Scaman +2

In machine unlearning, $(ε, I^´) -$ unlearning is a popular framework that provides formal guarantees on the effectiveness of the removal of a subset of training data, the fo…

stat.ML2025

When to Forget? Complexity Trade-offs in Machine Unlearning

Martin Van Waerebeke, Marco Lorenzi, Giovanni Neglia +1

Machine Unlearning (MU) aims at removing the influence of specific data points from a trained model, striving to achieve this at a fraction of the cost of full model retraining. In…

Variance-Reduced (ε,I^´)−Unlearning using Forget Set Gradients

When to Forget? Complexity Trade-offs in Machine Unlearning

Variance-Reduced $(ε, I^´) -$ Unlearning using Forget Set Gradients